Hae LUTPubista
Aineistot 1-10 / 27
Predicting the customer churn with machine learning methods : case: private insurance customer data
(2019)
Customer churn prediction is a field that uses machine learning to predict whether a customer is going to leave the company or not. The goal of this thesis is to study the churn prediction field and apply the knowledge in ...
Predicting short-term traffic speed : a model assessment using spatiotemporal variables
The focus of the thesis is to examine different machine learning models’ ability to predict short-term traffic speed. An autoregressive model, ARIMA model, Linear Regression, K-Nearest Neighbor and Extreme Gradient Boosted ...
Deep reinforcement learning in portfolio management : policy gradient method for S&P-500 stock selection
(2019)
Tämän maisterintutkielman tavoitteena on tutkia syvän vahvistusoppimisen (deep reinforcement learning, DRL) soveltuvuutta salkunhoitoon S&P500-indeksin osakkeista koostuvan osakeportfolion riskikorjatun tuoton parantamiseksi. ...
Insurance claim risk scoring with machine learning algorithms: A case study on developing a predictive system for assessing corporate customers' claim risk
(2018)
Predictive learning algorithms offer tools to automate and improve insurance risk management. The aim of this thesis is to study classification algorithms in risk scoring applications and to evaluate them in the creation ...
Pricing financial call options with a multilayer perceptron class of artificial neural network : case: S&P 500 index options in 2017-2019
(2019)
The objective of this Master’s thesis is to examine if a Multilayer Perceptron class of artificial neural network can be applied to estimate European call option prices on the S&P 500 index in 2017 to 2019. The estimations ...
Neural network based binary and multi-class trading strategies using probability thresholds for trading actions on S&P 500 index
(2020)
There have been many attempts to predict stock market returns using regression algorithms. However, from the viewpoint of an investor, the stock market can be interpreted as a classification problem with the decision to ...
Konkurssin ennustaminen koneoppimisen avulla pienissä suomalaisissa palvelualan yrityksissä
(2021)
Tämän kandidaatintutkielman tavoitteena on muodostaa koneoppimiseen perustuva konkurssinennustamismalli. Tutkimus käsittelee konkurssiyrityksen tunnistamista maksuhäiriöriskiltä suojautumisen työkaluna. Aihetta tutkitaan ...
Segmentation of investor customers using machine learning in banking
(2021)
The purpose of this study is to analyze customer data from a local retail bank using machine learning. The goal is to detect attributes that investment customers have. Furthermore, this study compares performances of ...
Identifying drivers of forecasting model performance for highly intermittent SKU demand
(2021)
In the area of demand forecasting, stock-keeping unit (SKU) demand forecasting for inventory management presents a unique challenge to the forecaster because of its high levels of intermittency (frequent zero-demand periods). ...
Real estate insurance claims prediction with machine learning algorithms
(2022)
Nowadays insurance companies are increasingly implementing machine learning algorithms in their business routine. An ability to determine beforehand an emergence of claims could offer a tool to increase a profitability of ...